PulseAugur
中
实时 00:27:28
English(EN) VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

VisCo框架使用LLM进行高效视觉令牌压缩

研究人员开发了VisCo,一个用于压缩视觉语言模型(VLM)中视觉令牌的新型框架。与需要大量重新训练或外部模块的先前方法不同,VisCo利用VLM的现有能力作为内在压缩器。这种训练高效的方法使用带有内存令牌的参数共享自编码器来压缩视觉信息,在各种压缩比下均表现出优越的性能,甚至在与原始令牌结合时也能改进基础模型。 AI

影响 该方法可以显著降低视觉语言模型的推理延迟和内存需求,从而实现更高效的部署和更广泛的可访问性。

排序理由 该集群包含一篇学术论文,详细介绍了VLM中视觉令牌压缩的新方法。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

VisCo框架使用LLM进行高效视觉令牌压缩

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇学术论文,详细介绍了VLM中视觉令牌压缩的新方法。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
86 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Yupeng Zheng, Kai Zou, Bin Liu, Nenghai Yu ·

    VisCo:利用大型语言模型作为内在编码器进行视觉令牌压缩

    arXiv:2607.12756v1 Announce Type: new Abstract: Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference latency and memory overhead. This has motivated extensive research on visual token compression. While training-free strategies …

  2. arXiv cs.CV TIER_1 English(EN) · Nenghai Yu ·

    VisCo:利用大型语言模型作为内在编码器进行视觉令牌压缩

    Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference latency and memory overhead. This has motivated extensive research on visual token compression. While training-free strategies rely on heuristic metrics and suffer significant…